# A tibble: 2 × 2
group mean
<chr> <dbl>
1 Placebo 18.3
2 Semaglutide 36.7
[1] 18.45558
[1] 9.035466e-13
Departments of Medicine, Epidemiology and Biostatistics, McGill University
2025-04-26
STRIDE was a double-blind, randomised, placebo-controlled trial done at 112 outpatient clinical trial sites in 20 countries in North America, Asia, and Europe. Participants were aged 18 years and older, with type 2 diabetes and peripheral artery disease with intermittent claudication.
Participants were randomly assigned (1:1) using an interactive web response system to receive subcutaneous semaglutide 1·0 mg once per week for 52 weeks or placebo.
The primary endpoint was the ratio to baseline of the maximum walking distance at week 52 measured on a constant load treadmill in the full analysis set.
# A tibble: 2 × 2
group mean
<chr> <dbl>
1 Placebo 18.3
2 Semaglutide 36.7
[1] 18.45558
[1] 9.035466e-13
Example RoB2.0 tool for randomized controlled trials
Example RoB2.0 tool for randomized controlled trials Traffic lights format
# A tibble: 792 × 6
group treat baseline_true baseline_obs followup change
<chr> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Semaglutide 1 166. 142. 147. 5.02
2 Semaglutide 1 171. 142. 148. 5.98
3 Semaglutide 1 174. 149. 182. 33.1
4 Semaglutide 1 200. 213. 194. -18.8
5 Semaglutide 1 222. 211. 249. 38.1
6 Semaglutide 1 200. 196. 206. 9.19
7 Semaglutide 1 163. 139. 167. 28.3
8 Semaglutide 1 172. 174. 178. 4.14
9 Semaglutide 1 153. 131. 168. 37.4
10 Semaglutide 1 170. 139. 158. 18.8
# ℹ 782 more rows
Naive Analysis (Wrong)
[1] 19.62093
[1] 1.727469e-20
Correct Analysis: ANCOVA
Call:
lm(formula = followup ~ treat + baseline_obs, data = df)
Residuals:
Min 1Q Median 3Q Max
-91.273 -16.333 0.104 15.567 91.224
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 101.10181 5.83737 17.320 < 2e-16 ***
treat 13.68387 1.78125 7.682 4.64e-14 ***
baseline_obs 0.46234 0.03083 14.995 < 2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 24.6 on 789 degrees of freedom
Multiple R-squared: 0.2398, Adjusted R-squared: 0.2379
F-statistic: 124.5 on 2 and 789 DF, p-value: < 2.2e-16
Running MCMC with 4 sequential chains...
Chain 1 finished in 1.3 seconds.
Chain 2 finished in 1.5 seconds.
Chain 3 finished in 1.5 seconds.
Chain 4 finished in 1.7 seconds.
All 4 chains finished successfully.
Mean chain execution time: 1.5 seconds.
Total execution time: 6.5 seconds.
# A tibble: 1 × 10
variable mean median sd mad q5 q95 rhat ess_bulk ess_tail
<chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 adj_diff 13.7 13.7 1.79 1.76 10.7 16.6 1.00 4128. 3683.
Suppose we randomly remove 15% of the data, and the missingness is biased toward the treatment group
For example if the top 15% of placebo performers were lost and the poorest 15% of treatment group
This will inflate the treatment effect.
[1] "Remember the unbiased (but faulty) analysis was: 19.6"
[1] "The biased analysis was: 35.6"
Conclusion: Trial of SGLT-2 inhibitors in 1257 TAVI patients undergoing TAVI reported significantly lower incidence of death from any cause or worsening of heart failure than standard care alone.
Justification: SGLT2i reduce the HF risk of heart-failure but valvular patients have been excluded from randomized trials.
Academic half day - journal club